Luke Metz

Virginia Smith

CoRR, 2023

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies.

[BibT_eX]

[DOI]

Oscar Li

Virginia Smith

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Transformer-Based Learned Optimization.

[BibT_eX]

[DOI]

Cristian Sminchisescu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

General-Purpose In-Context Learning by Meta-Learning Transformers.

[BibT_eX]

[DOI]

Louis Kirsch

CoRR, 2022

VeLO: Training Versatile Learned Optimizers by Scaling Up.

[BibT_eX]

[DOI]

CoRR, 2022

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases.

[BibT_eX]

[DOI]

Christian Schröder de Witt

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Discovered Policy Optimisation.

[BibT_eX]

[DOI]

Jakob N. Foerster

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract).

[BibT_eX]

[DOI]

Paul Vicol

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

Practical Tradeoffs between Memory, Compute, and Performance in Learned Optimizers.

[BibT_eX]

[DOI]

Proceedings of the Conference on Lifelong Learning Agents, 2022

Lyapunov Exponents for Diversity in Differentiable Games.

[BibT_eX]

[DOI]

Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 2022

2021

Gradients are Not All You Need.

[BibT_eX]

[DOI]

CoRR, 2021

Training Learned Optimizers with Randomly Initialized Learned Optimizers.

[BibT_eX]

[DOI]

C. Daniel Freeman

CoRR, 2021

Reverse engineering learned optimizers reveals known and novel mechanisms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies.

[BibT_eX]

[DOI]

Paul Vicol

Proceedings of the 38th International Conference on Machine Learning, 2021

On Linear Identifiability of Learned Representations.

[BibT_eX]

[DOI]

Geoffrey Roeder

Durk Kingma

Proceedings of the 38th International Conference on Machine Learning, 2021

Learn2Hop: Learned Optimization on Rough Landscapes.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Parallel Training of Deep Networks with Local Updates.

[BibT_eX]

[DOI]

Pieter Abbeel

CoRR, 2020

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves.

[BibT_eX]

[DOI]

CoRR, 2020

On Linear Identifiability of Learned Representations.

[BibT_eX]

[DOI]

Geoffrey Roeder

Diederik P. Kingma

CoRR, 2020

Using a thousand optimization tasks to learn hyperparameter search strategies.

[BibT_eX]

[DOI]

CoRR, 2020

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian.

[BibT_eX]

[DOI]

Alexander Peysakhovich

Aldo Pacchiano

Jakob N. Foerster

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Learning an Adaptive Learning Rate Schedule.

[BibT_eX]

[DOI]

CoRR, 2019

Using learned optimizers to make models robust to input noise.

[BibT_eX]

[DOI]

Jonathon Shlens

Ekin D. Cubuk

CoRR, 2019

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction.

[BibT_eX]

[DOI]

C. Daniel Freeman

David Ha

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Understanding and correcting pathologies in the training of learned optimizers.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Guided evolutionary strategies: augmenting random search with surrogate gradients.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Meta-Learning Update Rules for Unsupervised Representation Learning.

[BibT_eX]

[DOI]

Brian Cheung

Proceedings of the 7th International Conference on Learning Representations, 2019

Towards GAN Benchmarks Which Require Generalization.

[BibT_eX]

[DOI]

Ishaan Gulrajani

Colin Raffel

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Learned optimizers that outperform SGD on wall-clock and test loss.

[BibT_eX]

[DOI]

CoRR, 2018

Guided evolutionary strategies: escaping the curse of dimensionality in random search.

[BibT_eX]

[DOI]

George Tucker

CoRR, 2018

Learning Unsupervised Learning Rules.

[BibT_eX]

[DOI]

Brian Cheung

CoRR, 2018

Learning to Learn Without Labels.

[BibT_eX]

[DOI]

Brian Cheung

Proceedings of the 6th International Conference on Learning Representations, 2018

Adversarial Spheres.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Discrete Sequential Prediction of Continuous Actions for Deep RL.

[BibT_eX]

[DOI]

CoRR, 2017

BEGAN: Boundary Equilibrium Generative Adversarial Networks.

[BibT_eX]

[DOI]

David Berthelot

Tom Schumm

CoRR, 2017

Unrolled Generative Adversarial Networks.

[BibT_eX]

[DOI]

Ben Poole

David Pfau

Proceedings of the 5th International Conference on Learning Representations, 2017

2016

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.

[BibT_eX]

[DOI]

Alec Radford